Jeih-weih HungJia-Lin ShenLin-Shan LeeImproved parallel model combination techniques with split Gaussian mixtures for speech recognition under noisy conditions.437-4401999ICASSPhttps://doi.org/10.1109/ICASSP.1999.758156https://doi.ieeecomputersociety.org/10.1109/ICASSP.1999.758156conf/icassp/1999db/conf/icassp/icassp1999.html#HungSL99